Stacked Denoising Autoencoder network for short-term prediction of electrical Algerian load

Short-term load forecasting is a topic of considerable interest; it ensures the balance between the production and consumption one day ahead. In this paper, time series models have been developed to provide an efficient forecast for electricity consumption in Algeria using Deep Neural Networks in th...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International Conference on Control, Decision and Information Technologies (Online) Ročník 1; s. 189 - 194
Hlavní autoři: Hiba, Chelabi, Tarek, Khadir Mohamed, Belkacem, Chikhaoui
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 29.06.2020
Témata:
autoregressive variable
Biological system modeling
electricity consumption
Forecasting
Load modeling
MLP
Neural networks
Predictive models
SDAE
short-term load forecasting
Temperature distribution
time series
Time series analysis
ISSN:2576-3555
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Short-term load forecasting is a topic of considerable interest; it ensures the balance between the production and consumption one day ahead. In this paper, time series models have been developed to provide an efficient forecast for electricity consumption in Algeria using Deep Neural Networks in the form of Stacked Denoising Autoencoder (SDAE) and a regular Multilayer Perceptron (MLP) as a benchmark model. The obtained models are established and evaluated using the hourly temperature and electricity consumption data provided by the Algerian National Electricity and Gas Company (SONELGAZ). Convincing forecasting results for the Algerian national load were found and conclusions drawn.
ISSN:2576-3555
DOI:10.1109/CoDIT49905.2020.9263850